Retains visual content as real image outputs when requested: the portrait, donut chart, and bar chart are all returned as preserved figure/image crops rather than being dropped.
What was measured
Visual Content Retention
Retains charts, figures, diagrams, and images in the output and places them in the correct reading position.
decisive for this rankingtransformation
For complex PDFs, figures, charts, and images are part of the document content, so preserving them in the right place is part of the core job. (3 of 3 judges)
What was given, what came back
Test input: Hybrid Earnings Report · pdf · group: hybrid-earnings-report
Input — what we sent
Hybrid Earnings Report
A long, real-world hybrid annual report used to benchmark end-to-end PDF-to-markdown conversion. It combines native text, financial tables, charts/graphics, and scanned signature/stamp regions, stressing preservation of document structure, reading order, and embedded visual content across a multi-section report.
Why this input is hard
- · Native digital text extraction
- · Complex financial table preservation
- · Chart and graphic retention
- · Image-based signatures and stamps
- · Reading order across a long multi-section report
- · Markdown quality and consistency
Output — unretouched
Also checked on this input — same tool, 10 other criteria
Advanced Features✗ FailedOn the bar-chart schema, extract.run gets only 3 of 5 Sales values right: 2011 and 2012 are silently pulled from a different table ($69.9B and $73.3B), with no confidence or warning signal.Advanced Features✓ WorkedThe separate schema-driven extract.run endpoint cleanly recovers both a financial table and a donut chart: all requested table rows and all five donut percentages come back exactly.Advanced Features◐ MixedThe parse pipeline’s confidence field catches all 10 footer-number corruptions and also produces one false alarm on a correct securities table, so the signal is real but not perfectly calibrated.Complex Document Handling◐ MixedProcesses the full 84-page mixed-content report in 25.5 seconds with no truncation and keeps the hardest nested table’s 27 values exact, but 10 footer numbers are corrupted in the back two-thirds of the file.Markdown Quality⚠ StruggledProduces usable but not clean markdown: the output contains 12 <signature> tags, 2 <empty> placeholders, and literal HTML tags such as <b>, <i>, and <u> instead of pure CommonMark.Reading Order & Structure⚠ StruggledDrops heading structure on most of the filing: the FORM 10-K opening area receives no # or ## markup, and the report says 80 of 84 pages stay as plain paragraphs rather than navigable section headings.Reading Order & Structure✓ WorkedLinearizes a two-column page correctly, reading the full left column, including all four bullets, before the right-column continuation appears, with no interleaving or sequence inversion.Table Preservation✗ FailedMis-merges two independent side-by-side lists into one table, forcing unrelated cost-of-sales and SG&A bullets into fake row pairs where no row correspondence exists in the source.Table Preservation✓ WorkedPreserves a genuinely row-paired 52-row state table as a clean grid, keeping the 1,792 stores total and 239,539 retail-square-footage total intact.Text & OCR Completeness✓ WorkedConverts the full 84-page native-digital annual report with no skipped pages; the output contains all 84 page-marker pairs, and checked high-risk numbers survive exactly, including the $51,550,988,273 market-value figure and 599,982,121 shares outstanding.
Provenance
- Observation
- d44d1388-5a3e-4021-94ac-d7281d773533
- Evidence run
- 6e3160de-fe46-4b45-b071-72560b5c5d0e
- Study
- Convert a Complex PDF into Clean Markdown with an API
- Research task
- 86b9h7t37
- Tested at
- not recorded
- Source
- first-party
- Evidence state
- verified
- Proof shown
- input + output shown
- Cost / latency
- not captured
- Repeat run
- not captured
- Tester
- not captured
The last three rows are honest blanks, not placeholders — our capture has no field for them yet.
Query this
get_evidence({
tool: "reducto",
scenario: "hybrid-earnings-report"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 8 other tools
measured on Visual Content Retention
Adobe API✓ WorkedKeeps embedded charts and segment graphics inside the report page rather than dropping them, so the extracted page still shows the financial-highlights block and segment-sales graphics.Extend AI◐ MixedRetains charts and logos as standalone figure blocks with captions, but they are extracted out of page position rather than embedded inline.Landing AI✗ FailedReplaces a waterfall chart with text, preserving the SG&A rate values and year-to-year change labels but not the chart as a visual asset in the output.LlamaParse◐ MixedRepresents logos and signatures as textual placeholders or descriptions rather than retaining them as image assets in the output.Mistral AI✓ WorkedVisual assets are extracted into page-specific folders, keeping charts, signatures, and other document elements tied to their source pages instead of collapsing them into one consolidated output.Nutrient.io◐ MixedKeeps the surrounding 3-signatory signature-page text, but does not extract the handwritten signatures themselves.Tensorlake✓ WorkedRetains scanned signature-page visuals as figure blocks plus signer text, including named executives and dates, rather than dropping the signature regions from the output.Upstage AI✗ FailedDoes not retain handwritten signature content as visual output on the signatures page, leaving only partial surrounding legal text and no clearly identifiable signatures.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com